Artificial Analysis · Agentic Index

We regularly fetch and display public benchmark data: LMArena user voting rankings, Epoch AI test scores, and OpenRouter usage rankings. Each leaderboard shows both its publication date and the date we retrieved it. These scores are not assigned by this site.

LMArena scores come from people comparing two models' answers side by side and voting for the better one, using an Elo-based system. If score differences fall within the confidence intervals, treat the models as roughly comparable.

How to read this leaderboard

What it measures: An index created by Artificial Analysis by combining evaluations of multistep agent tasks involving tool use.

How to read the score: Higher scores indicate better results on tool use and multistep task evaluations.

Caveats: Results may vary with the evaluation environment and tool setup, so they should not be assumed to match performance in the agent tools you actually use.

Insights from this ranking

The highest score is 57.9, achieved by Claude Fable 5.1 (Max, Default Fallback).
The gap between 1st and 5th place is 4.9.
Anthropic has the most models among the top 10, with 3.

Agentic Index Artificial Analysis

Published 2026-10-05 · Retrieved 2026-10-05

Claude Fable 5.1 (Max, Default Fallback)

57.9

Claude Opus 5 (Max)

56.5

Qwen3.8 Max (0902)

56.0

ZGLM-5.3 (Max)

53.1

xGrok 4.6 (High)

53.0

OGPT-6 Astra (max)

51.0

ZGLM 5.3 Flash

50.9

Claude Fable 5 (Max, Opus 4.8 Fallback)

50.7

OGPT-5.6 Sol (Max)

50.2

Qwen3.8 2.4T A95B

50.1

Kimi K3 (Max)

50.0

Qwen3.8 Max

49.9

Qwen3.8 27B (Xhigh)

45.8

Claude Sonnet 5 (Max)

43.6

Muse Spark 1.2 (Xhigh)

43.2

OGPT-5.6 Terra (Max)

43.2

OGPT-5.6 Luna (Max)

42.1

Claude Opus 4.8 (Max)

41.9

DeepSeek V4 Pro 0813 (Max)

41.3

xGrok 4.5 (High)

41.2

The chart shows only the highest-scoring reasoning setting, such as high or max, for each model. The table shows rankings for all settings.

View table (top 60)

Rank	Model	Developer	Score
1	#1Claude Fable 5.1 (Max, Default Fallback)	Anthropic	57.9
2	#2Claude Opus 5 (Max)	Anthropic	56.5
3	#3Qwen3.8 Max (0902)	Alibaba	56
4	#4ZGLM-5.3 (Max)	Z.ai	53.1
5	#5xGrok 4.6 (High)	xAI	53
6	#6OGPT-6 Astra (max)	OpenAI	51
7	#7ZGLM 5.3 Flash	Z.ai	50.9
8	#8Claude Fable 5 (Max, Opus 4.8 Fallback)	Anthropic	50.7
9	#9OGPT-5.6 Sol (Max)	OpenAI	50.2
10	#10Qwen3.8 2.4T A95B	Alibaba	50.1
11	#11Kimi K3 (Max)	Moonshot AI	50
12	#12Qwen3.8 Max	Alibaba	49.9
13	#13Qwen3.8 27B (Xhigh)	Alibaba	45.8
14	#14Claude Sonnet 5 (Max)	Anthropic	43.6
15	#15Muse Spark 1.2 (Xhigh)	Meta	43.2
16	#16OGPT-5.6 Terra (Max)	OpenAI	43.2
17	#17OGPT-5.6 Luna (Max)	OpenAI	42.1
18	#18Claude Opus 4.8 (Max)	Anthropic	41.9
19	#19DeepSeek V4 Pro 0813 (Max)	DeepSeek	41.3
20	#20xGrok 4.5 (High)	xAI	41.2
21	#21DeepSeek V4 Flash 0731 (Max)	DeepSeek	41
22	#22Gemini 3.8 Flash (High)	Google	40.2
23	#23Claude Opus 4.7 (Max)	Anthropic	38.6
24	#24ZGLM-5.2 (Max)	Z.ai	38.4
25	#25OGPT-5.5 (Xhigh)	OpenAI	36.4
26	#26Gemini 3.7 Flash (High)	Google	35.2
27	#27Claude Sonnet 4.6 (Max)	Anthropic	31.8
28	#28MiniMax-M3	MiniMax	29.5
29	#29Gemini 3.6 Flash (High)	Google	29
30	#30iLing-3.0-flash-VL	inclusionAI	28.7
31	#31iLing-3.0-flash-Fin	inclusionAI	27.9
32	#32DeepSeek V4 Flash 0420 (High)	DeepSeek	26.3
33	#33DeepSeek V4 Pro 0424 (Max)	DeepSeek	26.3
34	#34Gemini 3.5 Flash (High)	Google	26
35	#35Muse Spark 1.1 (Xhigh)	Meta	25.8
36	#36THy3	Tencent	24.1
37	#37ZGLM-5.1 (Reasoning)	Z.ai	23.9
38	#38NNex-N2-Pro (Based on Qwen3.5-397B-A17B)	Nex Agi	23.7
39	#39TInkling Small	Thinkingmachines	23.5
40	#40TInkling (Xhigh)	Thinkingmachines	22.5
41	#41Qwen3.7 Max	Alibaba	22.5
42	#42MiMo-V2.5-Pro (Reasoning)	Xiaomi	21.3
43	#43Kimi K2.7 Code	Moonshot AI	21
44	#44Kimi K2.6 (Reasoning)	Moonshot AI	20.5
45	#45Nemotron 3 Ultra 550B A55B (Reasoning)	NVIDIA	20.1
46	#46iLing 3.0 Flash	inclusionAI	19.3
47	#47Qwen3.6 27B (Reasoning)	Alibaba	18.5
48	#48OGPT-5.4 mini (Xhigh)	OpenAI	17.9
49	#49Qwen3.7 Plus	Alibaba	17.5
50	#50OGPT-5.4 nano (Xhigh)	OpenAI	16
51	#51Claude 4.5 Sonnet (Reasoning)	Anthropic	15.8
52	#52MiMo-V2.5	Xiaomi	15.8
53	#53xGrok 4.3 (High)	xAI	15.5
54	#54MiniMax-M2.7	MiniMax	15.3
55	#55Gemini 3.5 Flash-Lite	Google	14.3
56	#56MLongCat 2.0	Meituan	14
57	#57Qwen3.6 35B A3B (Reasoning)	Alibaba	13.1
58	#58iRing-2.6-1T	inclusionAI	10.7
59	#59Qwen3.5 397B A17B (Reasoning)	Alibaba	8.3
60	#60Gemini 3.1 Pro Preview	Google	8.2

Source: Artificial Analysis (artificialanalysis.ai) via OpenRouter (openrouter.ai/rankings). Licensed under CC BY 4.0.

Data: LMArena leaderboard dataset (CC BY 4.0). Changes: Top 50 entries per leaderboard; scores are rounded. https://huggingface.co/datasets/lmarena-ai/leaderboard-datasetCompany logos are trademarks of their respective owners and are used only for identification (icons: Simple Icons).Data: Epoch AI — Capabilities & benchmarking (CC BY 4.0). https://epoch.ai/benchmarksSource: Artificial Analysis (artificialanalysis.ai) via OpenRouter (openrouter.ai/rankings). Source: OpenRouter evals (openrouter.ai) via OpenRouter (openrouter.ai/rankings). Source: Design Arena (www.designarena.ai) via OpenRouter (openrouter.ai/rankings). Licensed under CC BY 4.0. Source: OpenRouter (openrouter.ai/rankings), as of 2026-10-05. Licensed under CC BY 4.0. https://openrouter.ai/rankings